Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    structural elements and metadata in texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.70
     he
    -0.52
     prensa
    -0.51
     grazia
    -0.51
     ragazzi
    -0.50
     vostri
    -0.50
     célèbres
    -0.49
     populaires
    -0.48
     amistad
    -0.48
     popoli
    -0.48
    POSITIVE LOGITS
    1.00
    })));
    0.97
    ſelf
    0.95
    ".
    0.93
    ſelves
    0.91
    ."</
    0.91
    "):
    0.90
    脚注の使い方
    0.89
    ).</
    0.88
    '):
    0.87
    Act Density 1.143%

    No Known Activations